Research map / Label-efficient and robust learning / Recognition and long-tail
NM-Net: Mining Reliable Neighbors for Robust Feature Correspondences
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use NM-Net instead of LGC-Net | feature correspondence selection · NARROW | F-measure (%): 96.611 -> 97.501 | Helped |
| use NM-Net instead of LGC-Net | feature correspondence selection · WIDE | F-measure (%): 91.264 -> 93.145 | Helped |
| use NM-Net instead of LGC-Net | feature correspondence selection · COLMAP | F-measure (%): 33.949 -> 38.887 | Helped |
| use NM-Net instead of LGC-Net | feature correspondence selection · MULTI | F (%): 41.849 -> 35.605 | Hurt |
| replace spatial kNN with compatibility-specific kNN (ablation) | NM-Net · NARROW | F-measure (%): 97.283 -> 97.501 | Helped |
| replace spatial kNN with compatibility-specific kNN (ablation) | NM-Net · WIDE | F-measure (%): 92.749 -> 93.145 | Helped |
| replace spatial kNN with compatibility-specific kNN (ablation) | NM-Net · COLMAP | F-measure (%): 37.503 -> 38.887 | Helped |
| vary neighbor count from the default to 4 or 32 (ablation) | NM-Net · NARROW, WIDE, and COLMAP | performance | Hurt |
| increase neighbor count to 32 (ablation) | NM-Net · inlier neighbor graphs | neighbor consistency | Hurt |
| decrease neighbor count to 4 (ablation) | NM-Net · NARROW, WIDE, and COLMAP | performance | Hurt |
Closest papers by meaning
- Progressive Neighbor Consistency Mining for Correspondence Pruning (CVPR 2023 · similarity 0.91)
- Correspondence Networks With Adaptive Neighbourhood Consensus (CVPR 2020 · similarity 0.87)
- Neighbourhood Consensus Networks (NeurIPS 2018 · similarity 0.87)
- MGNet: Learning Correspondences via Multiple Graphs (AAAI 2024 · similarity 0.84)
- ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses (NeurIPS 2024 · similarity 0.84)
- FC-GNN: Recovering Reliable and Accurate Correspondences from Interferences (CVPR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.